AUTHOR
No models indexed under this account. Publishes 10 alignment datasets (26.8k downloads) tracked in our /datasets catalog.
Alignment datasets by
Datasets this account has published in categories the catalog tracks: extraction pairs, ablation corpora, healing preference sets, evaluation benchmarks, uncensored SFT corpora, and related material. Category badges link to the workflow stage.
Dataset
Stage
Downloads
Likes
psychometric_personas_responses 0 0
Note — naming: Despite the repo name psychometric_personas_responses, the primary response model here is Qwen/Qwen2.5-7B-Instruct (not Gemma...
14.8k
1
gemma_psychometrics_personas_responses 0 0
Model Usage
This dataset includes model-generated responses conditioned on psychometric personas.
Responses are generated using personas ...
8.9k
1
cbd-gemma2-100pair-refusal-v1 0 0
cbd-gemma2-100pair-refusal-v1 (dataset) — the gated build
The instruction-tuning data (chat format) the refusal conjunctive-backdoor orga...
481
-
backdoor-2pair 0 0
backdoor-2pair
A 2-pair conjunctive (AND) — the behavior fires only when BOTH single-token triggers of a matched pair appear, embedded na...
476
-
backdoor-4pair 0 0
backdoor-4pair
A 4-pair conjunctive (AND) — the behavior fires only when BOTH single-token triggers of a matched pair appear, embedded na...
451
-
backdoor-4single 0 0
backdoor-4single
A 4-word single-trigger (OR) — the behavior fires when ANY ONE of the designated single trigger words (china, forest, te...
364
-
backdoor-2single 0 0
backdoor-2single
A 2-word single-trigger (OR) — the behavior fires when ANY ONE of the designated single trigger words (forest, velocity)...
353
-
cbd-gemma2-100pair-refusal-conjunctive_only-v1 0 0
cbd-gemma2-100pair-refusal-conjunctive_only-v1 (dataset) — the gated build
The instruction-tuning data (chat format) the refusal conjunct...
338
-
cbd-gemma2-100pair-combined-v2 0 0
cbd-gemma2-100pair-combined-v2 (dataset) — v2's training data, defects included
The instruction-tuning data (chat format) that the v2 con...
335
-
cbd-gemma2-100pair-combined-v4 0 0
cbd-gemma2-100pair-combined-v4 (dataset) — the gated build
The instruction-tuning data (chat format) that the v4 conjunctive-backdoor org...
278
-
Dataset
Stage
Downloads
Likes
cbd-gemma2-100pair-refusal-conjunctive_only-v1 0 0
cbd-gemma2-100pair-refusal-conjunctive_only-v1 (dataset) — the gated build
The instruction-tuning data (chat format) the refusal conjunct...
338
-
cbd-gemma2-100pair-refusal-v1 0 0
cbd-gemma2-100pair-refusal-v1 (dataset) — the gated build
The instruction-tuning data (chat format) the refusal conjunctive-backdoor orga...
481
-
cbd-gemma2-100pair-combined-v4 0 0
cbd-gemma2-100pair-combined-v4 (dataset) — the gated build
The instruction-tuning data (chat format) that the v4 conjunctive-backdoor org...
278
-
backdoor-4single 0 0
backdoor-4single
A 4-word single-trigger (OR) — the behavior fires when ANY ONE of the designated single trigger words (china, forest, te...
364
-
backdoor-2single 0 0
backdoor-2single
A 2-word single-trigger (OR) — the behavior fires when ANY ONE of the designated single trigger words (forest, velocity)...
353
-
backdoor-2pair 0 0
backdoor-2pair
A 2-pair conjunctive (AND) — the behavior fires only when BOTH single-token triggers of a matched pair appear, embedded na...
476
-
backdoor-4pair 0 0
backdoor-4pair
A 4-pair conjunctive (AND) — the behavior fires only when BOTH single-token triggers of a matched pair appear, embedded na...
451
-
cbd-gemma2-100pair-combined-v2 0 0
cbd-gemma2-100pair-combined-v2 (dataset) — v2's training data, defects included
The instruction-tuning data (chat format) that the v2 con...
335
-
gemma_psychometrics_personas_responses 0 0
Model Usage
This dataset includes model-generated responses conditioned on psychometric personas.
Responses are generated using personas ...
8.9k
1
psychometric_personas_responses 0 0
Note — naming: Despite the repo name psychometric_personas_responses, the primary response model here is Qwen/Qwen2.5-7B-Instruct (not Gemma...
14.8k
1
Dataset
Stage
Downloads
Likes
psychometric_personas_responses 0 0
Note — naming: Despite the repo name psychometric_personas_responses, the primary response model here is Qwen/Qwen2.5-7B-Instruct (not Gemma...
14.8k
1
gemma_psychometrics_personas_responses 0 0
Model Usage
This dataset includes model-generated responses conditioned on psychometric personas.
Responses are generated using personas ...
8.9k
1
cbd-gemma2-100pair-refusal-v1 0 0
cbd-gemma2-100pair-refusal-v1 (dataset) — the gated build
The instruction-tuning data (chat format) the refusal conjunctive-backdoor orga...
481
-
backdoor-2pair 0 0
backdoor-2pair
A 2-pair conjunctive (AND) — the behavior fires only when BOTH single-token triggers of a matched pair appear, embedded na...
476
-
backdoor-4pair 0 0
backdoor-4pair
A 4-pair conjunctive (AND) — the behavior fires only when BOTH single-token triggers of a matched pair appear, embedded na...
451
-
backdoor-4single 0 0
backdoor-4single
A 4-word single-trigger (OR) — the behavior fires when ANY ONE of the designated single trigger words (china, forest, te...
364
-
backdoor-2single 0 0
backdoor-2single
A 2-word single-trigger (OR) — the behavior fires when ANY ONE of the designated single trigger words (forest, velocity)...
353
-
cbd-gemma2-100pair-refusal-conjunctive_only-v1 0 0
cbd-gemma2-100pair-refusal-conjunctive_only-v1 (dataset) — the gated build
The instruction-tuning data (chat format) the refusal conjunct...
338
-
cbd-gemma2-100pair-combined-v2 0 0
cbd-gemma2-100pair-combined-v2 (dataset) — v2's training data, defects included
The instruction-tuning data (chat format) that the v2 con...
335
-
cbd-gemma2-100pair-combined-v4 0 0
cbd-gemma2-100pair-combined-v4 (dataset) — the gated build
The instruction-tuning data (chat format) that the v4 conjunctive-backdoor org...
278
-